Review

[논문리뷰] HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained Travel

Yong Liu이 arXiv에 게시한 'HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained Travel' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Agent Planning #Hierarchical Reinforcement Learning #Constrained Optimization #Large Language Models (LLMs)#Travel Itinerary Generation #Constraint Drift #Parallel Execution #Resource Allocation

2026년 3월 8일

[논문리뷰] FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling

Bingning Wang이 arXiv에 게시한 'FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling' 논문에 대한 자세한 리뷰입니다.

#Review #Long-Context LLMs #Prefilling #Sparse Attention #Pattern Discovery #Dynamic Thresholding #Attention Speedup #Transformer Optimization

2026년 3월 8일

[논문리뷰] Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey

John D. Kelleher이 arXiv에 게시한 'Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Inference #Model Routing #Model Cascading #Efficiency Optimization #Dynamic Model Selection #Multi-LLM Systems #Cost-Performance Trade-off #Adaptive AI Systems

2026년 3월 8일

[논문리뷰] Dynamic Chunking Diffusion Transformer

arXiv에 게시된 'Dynamic Chunking Diffusion Transformer' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformer #Dynamic Chunking #Adaptive Patching #Image Generation #Computational Efficiency #Token Reduction #Spatial Segmentation #Load Balancing

2026년 3월 8일

[논문리뷰] Demystifying Action Space Design for Robotic Manipulation Policies

Jianxiong Li이 arXiv에 게시한 'Demystifying Action Space Design for Robotic Manipulation Policies' 논문에 대한 자세한 리뷰입니다.

#Review #Robotic Manipulation #Action Space Design #Imitation Learning #Delta Actions #Joint Space Control #Task Space Control #Generalization #Control Stability

2026년 3월 8일

[논문리뷰] DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation

arXiv에 게시된 'DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Systems #Presentation Generation #Large Language Models (LLMs)#Multimodal LLMs (MLLMs)#Environment-Grounded Reflection #Self-Correction #Dual-Agent Framework #Supervised Fine-tuning

2026년 3월 8일

[논문리뷰] Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations

Shuliang Liu이 arXiv에 게시한 'Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Vector Retrieval #Visual Document Understanding #Document Parsing #Layout-Informed Embeddings #Information Bottleneck #Storage Efficiency #Late Interaction

2026년 3월 8일

[논문리뷰] BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning

arXiv에 게시된 'BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Reinforcement Learning #Trust Region #Policy Optimization #Ratio Clipping #f-divergence #Entropy Regularization #Exploration #BandPO

2026년 3월 8일

[논문리뷰] UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data

Jia Zeng이 arXiv에 게시한 'UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data' 논문에 대한 자세한 리뷰입니다.

#Review #Dexterous Grasping #Bimanual Robots #Synthetic Data #Grasp Synthesis #Sim-to-Real Transfer #Point Cloud #Transformer Policy

2026년 3월 5일

[논문리뷰] Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline

arXiv에 게시된 'Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Lifelong Understanding #Video Dataset #Agentic AI #Dynamic Memory Management #Long-Context MLLMs #Temporal Reasoning #Concept Drift

2026년 3월 5일

[논문리뷰] Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling

arXiv에 게시된 'Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling' 논문에 대한 자세한 리뷰입니다.

#Review #Time Series Forecasting #Foundation Model #Mixture-of-Experts (MoE)#Serial Scaling #Transformer #Pre-training #Probabilistic Forecasting #Data Augmentation

2026년 3월 5일

[논문리뷰] SkillNet: Create, Evaluate, and Connect AI Skills

arXiv에 게시된 'SkillNet: Create, Evaluate, and Connect AI Skills' 논문에 대한 자세한 리뷰입니다.

#Review #AI Agents #Skill Management #Knowledge Engineering #Skill Ontology #Multi-dimensional Evaluation #LLM-based Agents #Skill Reuse #Transferable Mastery

2026년 3월 5일

[논문리뷰] SageBwd: A Trainable Low-bit Attention

arXiv에 게시된 'SageBwd: A Trainable Low-bit Attention' 논문에 대한 자세한 리뷰입니다.

#Review #Low-bit Attention #Quantization #Model Training #Pre-training #Backward Pass #QK-norm #SageBwd #Deep Learning Optimization

2026년 3월 5일

[논문리뷰] STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification

arXiv에 게시된 'STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-modal Re-Identification #Segmentation-Guided Feature Modulation #Token Modulation #Cross-Modal Interaction #Hypergraph Neural Networks #Object ReID #Transformer #SAM

2026년 3월 5일

[논문리뷰] RoboPocket: Improve Robot Policies Instantly with Your Phone

arXiv에 게시된 'RoboPocket: Improve Robot Policies Instantly with Your Phone' 논문에 대한 자세한 리뷰입니다.

#Review #Robot Learning #Imitation Learning #Policy Iteration #Augmented Reality #Visual Foresight #Data Collection #Human-in-the-Loop #Smartphone

2026년 3월 5일

[논문리뷰] RealWonder: Real-Time Physical Action-Conditioned Video Generation

Hong-Xing Yu이 arXiv에 게시한 'RealWonder: Real-Time Physical Action-Conditioned Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Physics Simulation #Real-Time #Action-Conditioned #3D Scene Reconstruction #Diffusion Models #Optical Flow

2026년 3월 5일

[논문리뷰] On-Policy Self-Distillation for Reasoning Compression

Zhipeng Wang이 arXiv에 게시한 'On-Policy Self-Distillation for Reasoning Compression' 논문에 대한 자세한 리뷰입니다.

#Review #Reasoning Compression #Self-Distillation #On-Policy Learning #Large Language Models #Mathematical Reasoning #Knowledge Distillation #Efficient Inference

2026년 3월 5일

[논문리뷰] Mozi: Governed Autonomy for Drug Discovery LLM Agents

arXiv에 게시된 'Mozi: Governed Autonomy for Drug Discovery LLM Agents' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Drug Discovery #Governed Autonomy #Multi-Agent System #Workflow Orchestration #Human-in-the-Loop #Computational Biology #Reproducibility

2026년 3월 5일

[논문리뷰] MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier

arXiv에 게시된 'MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier' 논문에 대한 자세한 리뷰입니다.

#Review #Scientific Discovery #LLM Training #Combinatorial Complexity #Hierarchical Search #Bounded Composition #Motivation Planning #Tractable Training #TOMATO-STAR Dataset

2026년 3월 5일

[논문리뷰] MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models

arXiv에 게시된 'MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Post-Training Quantization #Modality-Aware Smoothing #Cross-Modal Compensation #Quantization #Model Compression #SVD-based Whitening

2026년 3월 5일